Transformers
Safetensors
English
function calling
tool use
llama
llama3
tinyllama
instruct-tuned
4-bit quantization
ggfu
text-generation-inference
unsloth
trl
Instructions to use unclecode/tinyllama-function-call-lora-adapter-250424 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unclecode/tinyllama-function-call-lora-adapter-250424 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("unclecode/tinyllama-function-call-lora-adapter-250424", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Ctrl+K